Steering vectors from frozen LM layers enable a lightweight classifier to detect machine-generated text robustly across domains, source models, and editing attacks.
International Journal of Critical Infrastructure Protection 51, 100793
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Interconnected energy and transportation networks are modeled with real city data to quantify robustness to natural or synthetic disruptions using unweighted and weighted connectivity metrics.
citing papers explorer
-
SV-Detect: AI-generated Text Detection with Steering Vectors
Steering vectors from frozen LM layers enable a lightweight classifier to detect machine-generated text robustly across domains, source models, and editing attacks.